As both a computer scientist and a musician, Gus Xia designs intelligent systems that understand and extend human musical expression. To "understand" means to model the musical expression conveyed through acoustic, gestural, and emotional signals. To "extend" means to use this understanding to create expressive, interactive, and autonomous agents, serving both amateur and professional musicians. In particular, Xia creates interactive performers that are able to perform expressively in concert with humans by learning musicianship from rehearsal experience. Xia's study unifies machine learning and knowledge representation of music structure and performance skills in an HCI framework. In this talk, Xia will go over the learning techniques and present robot musicians capable of playing interactively with humans while generating facial and gestural expressions. At the end, Xia will show the potential impacts of this study on the future of music appreciation, performance, and education.
Gus Xia is completing his Ph.D. in the Machine Learning Department at Carnegie Mellon University where he studies Machine Learning and Computer Music. His interdisciplinary research on Artificial Music Intelligence connects with Machine Learning, Computer Music. HCI, and Robotics. His papers have been published in top conferences and journals in Computer Music and Intelligent Systems, including NIME, ISMIR, AAMAS, and Computer Music Journal. In 2010, he received his undergraduate degree in Information Science with a minor in Psychology at Peking University. He is also a professional DI and XIAO (Chinese flute and vertical flute) player and currently a soloist of the Pitt Carpathian Ensemble. Prior to that, he was the prime soloist of the Chinese Music Institute (CMI) in Peking University, where he also served as the president and assistant conductor. His research lies in the intersection of Machine Learning, HCI, Robotics, and Computer Music. His representative works include human-computer interactive performances, autonomous dancing robots, smart music displays, and large-scale content-based music retrieval.
Keith Ross, Dean of Engineering and Computer Science, is the faculty host of this talk.